Jani Even

Distant talking robust speech recognition using late reflection components of room impulse response

We propose a robust and fast dereverberation technique for real-time speech recognition application. First, we effectively identify the late reflection components of the room impulse response. We use this information together with the concept of spectral subtraction (SS) to remove the late reflection components of the reverberant signal. In the absence of the clean speech in actual scenario, approximation is carried out in estimating the late reflection where the estimation error is corrected through multi-band SS. The multi-band coefficients are optimized during offline training and used in the actual online dereverberation. The proposed method performs better and faster than the relevant approach using multi-LPC and reverberant matched model. Moreover the proposed method is robust to speaker and microphone locations.

Fast Dereverberation for Hands-Free Speech Recognition

A robust dereverberation technique for real-time hands-free speech recognition application is proposed. Real-time implementation is made possible by avoiding time-consuming blind estimation. Instead, we use the impulse response by effectively identifying the late reflection components of it. Using this information, together with the concept of Spectral Subtraction (SS), we were able to remove the effects of the late reflection of the reverberant signal. After dereverberation, only the effects of the early component is left and used as input to the recognizer. In this method, multi-band SS is used in order to compensate for the error arising from approximation. We also introduced a training strategy to optimize the values of the multi-band coefficients to minimize the error.

Including human factors for planning comfortable paths

This work proposes a Human-Comfortable Path Planner (HCoPP) system for autonomous passenger vehicles. The aim is to create a path planner that improves the feeling of comfort of the passenger, this topic is different from collision free planning and it has not received much attention. For this purpose, in addition to the shortest distance constraint conventionally used in path planning, constraints related to relevant environmental features are introduced. For straight segments, the constraint is based on the lane-circulation pattern preferred by humans. In curved segments and intersections, the constraint takes into account the visibility. A multi-layered cost map is proposed to integrate these additional constraints. To compute the human-comfortable path, a graph search algorithm was implemented. The evaluation of the proposed approach was conducted by having 30 participants riding an autonomous robotic wheelchair. The paths computed by the proposed path planner were compared towards a state of the art shortest-distance path planner implemented in the navigation stack of ROS. Experimental results show that the paths computed by the proposed approach are perceived as more comfortable.

Semi-blind suppression of internal noise for hands-free robot spoken dialog system

The speech enhancement architecture presented in this paper is specifically developed for hands-free robot spoken dialog systems. It is designed to take advantage of additional sensors installed inside the robot to record the internal noises. First a modified frequency domain blind signal separation (FD-BSS) gives estimates of the noises generated outside and inside of the robot. Then these noises are canceled from the acquired speech by a multichannel Wiener post-filter. Some experimental results show the recognition improvement for a dictation task in presence of both diffuse background noise and internal noises.

Blind source separation using order statistics

This paper shows the possibility to blindly separate instantaneous mixtures of sources by means of a criterion exploiting order statistics. Properties of higher order statistics and second-order methods are first underlined. Then a brief description of the order statistics shows that they gather all these properties and a new criterion is proposed. Next an iterative algorithm able to simultaneously extract all the sources is developed. The last part is comparison of this algorithm with well-known methods (JADE and SOBI). The most striking result is the possibility to exploit together independence and correlation through the use of order statistics.

An improved permutation solver for blind signal separation based front-ends in robot audition

The model of the human/machine hands-free speech interface is defined as a point source (the user voice) and a diffuse background noise. This situation is very different from the usual cocktail party model, separation of a mixture of speeches, that is usually treated in frequency domain blind signal separation (FD-BSS). In particular, the fast permutation solvers proposed for the cocktail party model results in poor separation performance in this case. In order to resolve the permutation more efficiently, this paper proposes a new approach that exploits the statistical discrepancy between the target speech and the diffuse background noise.

Probabilistic approach for building auditory maps with a mobile microphone array

This paper presents a multi-modal sensor approach for mapping sound sources using an omni-directional microphone array on an autonomous mobile robot. A fusion of audio data (from the microphone array), odometry information and the laser range scan data (from the robot) was used to precisely localize and map the audio sources in an environment. An audio map is created while the robot is autonomously navigating through the environment by continuously generating audio scans with a steered response power (SRP) algorithm. Using the poses of the robot, rays are cast in the map in all directions given by the SRP. Then each occupied cell in the geometric map hit by a ray is assigned a likelihood of containing a sound source. This likelihood is derived from the SRP at that particular instant. Since the localization of the robot is probabilistic, the uncertainty in the pose of the robot in the geometric map is propagated to the occupied cells hit during the ray casting. This process is repeated while the robot is in motion and the map is updated after every audio scan. The generated sound maps were reused and the changes in the audio environment were updated by the robot as it identifies these changes.

Mapping sound emitting structures in 3D

This paper presents a framework for creating a 3D map of an environment that contains the probability of a geometric feature to emit a sound. The goal is to provide an automated tool for condition monitoring of plants. The map is created by a mobile platform equipped with a microphone array and laser range sensors. The microphone array is used to estimate the sound power received from different directions whereas the laser range sensors are used for estimating the platform pose in the environment. During navigation, a ray casting method projects the audio measurements made onboard the mobile platform to the map of the environment. Experimental results show that the created map is an efficient tool for sound source localization.

Using multiple microphone arrays and reflections for 3D localization of sound sources

We proposed a method for estimating sound source locations in a 3D space by integrating sound directions estimated by multiple microphone arrays and taking advantage of reflection information. Two types of sources with different directivity properties (human speech and loudspeaker speech) were evaluated for different positions and orientations. Experimental results showed the effectiveness of using reflection information, depending on the position and orientation of the sound sources relative to the array, walls, and the source type. The use of reflection information increased the source position detection rates by 10% on average and up to 60% for the best case.

Blind signal extraction based speech enhancement in presence of diffuse background noise

This paper presents a new frequency domain blind signal extraction (FD-BSE) method for the extraction of a target speech in presence of diffuse background noise. This is a fast alternative to frequency domain blind signal separation (FD-BSS) for hands-free speech interface. Like the FD-BSS approach, the speech signal is enhanced by using a nonlinear filter to suppress the noise estimated by the blind method. Simulation results in a realistic environment show the effectiveness of the proposed method.